INDEX

Explanations

references to various types of cabinets and storage units

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ument

-0.18

ernaut

-0.17

ordin

-0.16

 cÃ¡

-0.16

yb

-0.16

$MESS

-0.15

utenberg

-0.15

ÑģÑı

-0.15

suit

-0.15

cord

-0.15

POSITIVE LOGITS

ted

0.19

rio

0.19

 doors

0.19

maker

0.19

éĸĢ

0.18

aver

0.17

oose

0.17

 door

0.17

etry

0.17

ry

0.17

Activations Density 0.008%

references to various types of cabinets and storage units

No Comments

No Known Activations